A Discrete-Event and Monte Carlo-Based Simulation Model for Multi-Server Call Center Queueing Systems

Abstract

This study presents the implementation and performance evaluation of a multi-server queueing system model for call center operations using discrete-event simulation combined with Monte Carlo analysis. The objective is to analyze system performance under varying numbers of service agents to identify the optimal configuration that balances service efficiency and customer satisfaction. The model assumes that customer arrivals follow a Poisson distribution, while service times are exponentially distributed to represent realistic call handling behavior. Simulation experiments were conducted over eight-hour operational periods with server counts ranging from one to eight, each replicated 500 times for statistical robustness. Performance indicators such as average waiting time, server utilization, and Service Level Agreement (SLA) compliance were analyzed to measure system efficiency. Results show that increasing the number of servers significantly reduces average waiting time and enhances service level compliance. Configurations with five or more servers achieved average waiting times close to zero and over 99% compliance with the SLA, while maintaining moderate server utilization levels between 70% and 80%. These findings demonstrate that integrating discrete-event simulation with Monte Carlo methods provides an effective and reliable framework for evaluating service system performance, optimizing resource allocation, and supporting decision-making in call center management.